GLM 4.7 Flash TEE by NanoGPT — Specs, Pricing & Capabilities | whichllm

Model ID TEE/glm-4.7-flash

Provider NanoGPT

Family glm-flash

Status -

Knowledge Cutoff -

Release Date 2026-01-19

Input Modalities text

Output Modalities text

Context Window 203000

Input Limit 203000

Output Limit 65535

Tool Calling No

Reasoning No

Structured Output No

Temperature Control -

Open Weights No

Input Cost / 1M tokens $0.15

Output Cost / 1M tokens $0.50

Reasoning Cost / 1M tokens -

Cache Read Cost / 1M tokens -

Cache Write Cost / 1M tokens -